Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1143
    Prev
    Next
    INDEX
    Explanations

    words related to a person named "Till"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Till" and phrases related to time measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TABLE
    -0.74
    Premium
    -0.70
    Jane
    -0.67
    Loading
    -0.67
    GU
    -0.67
    GROUP
    -0.66
    Es
    -0.66
    BILITIES
    -0.65
    Cath
    -0.65
    iliary
    -0.65
    POSITIVE LOGITS
    ting
    1.00
    ted
    0.90
    unda
    0.85
    stad
    0.81
     Till
    0.76
     Nadu
    0.76
    stal
    0.74
    uminati
    0.74
    awar
    0.73
    umi
    0.73
    Activations Density 0.018%

    No Known Activations